• International Journal of Internet, Broadcasting and Communication
• /
• v.13 no.4
• /
• pp.135-142
• /
• 2021

Estimating the locations of workers in a shipyard is beneficial for a variety of applications such as selecting potential forwarders for transferring data in IoT services and quickly rescuing workers in the event of industrial disasters or accidents. In this work, we propose a human movement stream processing system for estimating worker locations in shipyards based on Apache Spark and TensorFlow serving. First, we use Apache Spark to process location data streams. Then, we design a worker location prediction model to estimate the locations of workers. TensorFlow serving manages and executes the worker location prediction model. When there are requirements from clients, Apache Spark extracts input data from the processed data for the prediction model and then sends it to TensorFlow serving for estimating workers' locations. The worker movement data is needed to evaluate the proposed system but there are no available worker movement traces in shipyards. Therefore, we also develop a mobility model for generating the workers' movements in shipyards. Based on synthetic data, the proposed system is evaluated. It obtains a high performance and could be used for a variety of tasksin shipyards.

• International Journal of Computer Science & Network Security
• /
• v.23 no.10
• /
• pp.89-96
• /
• 2023

Intrusion detection has been widely studied in both industry and academia, but cybersecurity analysts always want more accuracy and global threat analysis to secure their systems in cyberspace. Big data represent the great challenge of intrusion detection systems, making it hard to monitor and analyze this large volume of data using traditional techniques. Recently, deep learning has been emerged as a new approach which enables the use of Big Data with a low training time and high accuracy rate. In this paper, we propose an approach of an IDS based on cloud computing and the integration of big data and deep learning techniques to detect different attacks as early as possible. To demonstrate the efficacy of this system, we implement the proposed system within Microsoft Azure Cloud, as it provides both processing power and storage capabilities, using a convolutional neural network (CNN-IDS) with the distributed computing environment Apache Spark, integrated with Keras Deep Learning Library. We study the performance of the model in two categories of classification (binary and multiclass) using CSE-CIC-IDS2018 dataset. Our system showed a great performance due to the integration of deep learning technique and Apache Spark engine.

• Tuberculosis and Respiratory Diseases
• /
• v.72 no.6
• /
• pp.481-485
• /
• 2012

Background: Tracheostomy is a common procedure for patients requiring prolonged mechanical ventilation. However, the timing of tracheostomy is quite variable. This study was performed to find out the factors determining the timing of tracheostomy in medical intensive care unit (ICU). Methods: Patients who were underwent tracheostomy between January 2008 and December 2009 in the medical ICU of Seoul National University Hospital were included in this retrospective study. Results: Among the 59 patients, 36 (61.0%) were male. Median Acute Physiology And Chronic Health Evaluation (APACHE) II scores and Sequential Organ Failure Assessment scores on the admission day were 28 and 7, respectively. The decision of tracheostomy was made on 13 days, and tracheostomy was performed on 15 days after endotracheal intubation. Of the 59 patients, 21 patients received tracheostomy before 2 weeks (group I) and 38 were underwent after 2 weeks (group II). In univariate analysis, days until the decision to perform tracheostomy (8 vs. 14.5, p<0.001), days before tracheostomy (10 vs. 18, p<0.001), time delay for tracheostomy (2.1 vs. 3.0, p<0.001), cardiopulmonary resuscitation (19.0% vs. 2.6%, p=0.049), existence of neurologic problem (38.1% vs. 7.9%, p=0.042), APACHE II scores (24 vs. 30, p=0.002), and $PaO_2/FiO_2$ <300 mm Hg (61.9% vs. 91.1%, p=0.011) were different between the two groups. In multivariate analysis, APACHE II scores${\geq}20$ (odds ratio [OR], 12.44; 95% confidence interval [CI], 1.14~136.19; p=0.039) and time delay for tracheostomy (OR, 1.97; 95% CI, 1.11~3.55; p=0.020) were significantly associated with tracheostomy after 2 weeks. Conclusion: APACHE II scores${\geq}20$ and time delay for tracheostomy were associated with tracheostomy after 2 weeks.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.2
• /
• pp.103-116
• /
• 2017

In this paper, we present the design and implementation of a large-scale qualitative spatial reasoner, which can derive new qualitative spatial knowledge representing both topological and directional relationships between two arbitrary spatial objects in efficient way using Aparch Spark SQL. Apache Spark SQL is well known as a distributed parallel programming environment which provides both efficient join operations and query processing functions over a variety of data in Hadoop cluster computer systems. In our spatial reasoner, the overall reasoning process is divided into 6 jobs such as knowledge encoding, inverse reasoning, equal reasoning, transitive reasoning, relation refining, knowledge decoding, and then the execution order over the reasoning jobs is determined in consideration of both logical causal relationships and computational efficiency. The knowledge encoding job reduces the size of knowledge base to reason over by transforming the input knowledge of XML/RDF form into one of more precise form. Repeat of the transitive reasoning job and the relation refining job usually consumes most of computational time and storage for the overall reasoning process. In order to improve the jobs, our reasoner finds out the minimal disjunctive relations for qualitative spatial reasoning, and then, based upon them, it not only reduces the composition table to be used for the transitive reasoning job, but also optimizes the relation refining job. Through experiments using a large-scale benchmarking spatial knowledge base, the proposed reasoner showed high performance and scalability.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.5
• /
• pp.384-390
• /
• 2020

Purpose: Organophosphate insecticide poisoning can have clinically fatal results. This study aimed to evaluate the relationship between the neutrophil/lymphocyte ratio (NLR) and the occurrence of death in patients with organophosphate insecticide poisoning. Methods: For this retrospective study, data on patients with organophosphate insecticide poisoning who visited the emergency room between January 2008 and November 2018 were collected. The NLR was measured at the time of arrival in the emergency room. The patients were divided into survival and death groups. Results: Overall, 150 patients were enrolled: 15 (10%) in the death group and 135 (90%) in the survival group. In the univariate analysis, the following variables were significantly different between the two groups: age, white blood cell count, amylase level, creatinine level, Acute Physiology And Chronic Health Evaluation (APACHE) II score, and NLR. In the logistic regression analysis of variables with significant differences in the univariate analysis, there were significant differences between the two groups with respect to age, APACHE II score, and NLR. The NLR was significantly higher in the death group than in the survival group (20.83 ± 22.24 vs. 7.38 ± 6.06, p=0.036). Conclusion: High NLR in patients with organophosphate insecticide poisoning may be useful in predicting mortality.

• Tuberculosis and Respiratory Diseases
• /
• v.66 no.1
• /
• pp.27-32
• /
• 2009

Background: The management of patients with lung cancer has improved recently, and many of them will require admission to the medical intensive care unit (MICU). The aim of this study was to examine the clinical characteristics and to identify risk factors for mortality in patients with lung cancer admitted to the MICU. Methods: We conducted retrospective analysis on 88 patients with lung cancer admitted to the MICU between April 2004 and March 2008. Results: Of the 88 patients (mean age, 66 years), 71 patients (80.7%) had non-small cell lung cancer and 17 patients (19.3%) had small cell lung cancer. Distant metastasis were present in 79 patients (89.8%). The main reasons for MICU admission were acute respiratory failure (77.3%), sepsis (11.4%), and central nervous system dysfunction (4.5%). Mechanical ventilation was used in 54 patients (61.4%). Acute Physiology and Chronic Health Evaluation (APACHE) II score, length of MICU stay, need for mechanical ventilation, source of MICU admission were correlated with MICU mortality. The type of lung cancer and metastasis were not predictive factors of death in MICU. Conclusion: Most common reason for ICU admission was acute respiratory failure. Mortality rate of lung cancer patients admitted to the MICU was 65.9%. APACHE II score, length of ICU stay, need for mechanical ventilation, source of MICU admission were predicted factors of death in the MICU.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.11
• /
• pp.525-536
• /
• 2017

Purpose: The aim of this study was to identify the factors influencing ICU (intensive care units) length of stay of adult patients with critical illness. Methods: This study was adopted descriptive design. 270 patients who were admitted to ICU in general hospital, Seoul were analyzed. Results: A total of 270 patients, 116 (43%) patients had stayed more than 5 days. The length of stay of intensive care unit was significant positive correlation with the FCI(Functional Comobidity Index) score(r=0.33, p<.001) and APACHE(Aacute Physiology and Chronic Health Evlauaion) II(r=0.19, p=.001). In multiple logistic regression, the predictors of ICU length of stay were admission route (p=0.013), FCI score (p<0.001), APACHE II(p=0.012). Conclusions: Heatlh care providers in ICU should be aware that patients who admit to emergency departments and have higher disease severity are more considered to reduce their ICU length of stays.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.245-250
• /
• 2023

Digital twin technology, which copies information from real space into virtual space, is being used in a variety of fields.Interest in digital twins is increasing, especially in advanced manufacturing fields such as Industry 4.0-based smart manufacturing. Operating a digital twin system generates a large amount of data, and the data generated has different characteristics depending on the technology field, so it is necessary to efficiently manage resources and use an optimized digital twin platform technology. Research on digital twin pipelines has continued, mainly in the advanced manufacturing field, but research on high-speed pipelines suitable for data in the plant field is still lacking. Therefore, in this paper, we propose a pipeline design method that is specialized for digital twin data in the plant field that is rapidly poured through Apache Kafka. The proposed model applies plant information on a Revit basis. and collect plant-specific data through Apache Kafka. Equipped with a lightweight CFD engine, it is possible to create a digital twin model that is more suitable for the plant field than existing digital twin technology for the manufacturing field.

• KSCI Review
• /
• v.25 no.1
• /
• pp.1-6
• /
• 2017

• Defense and Technology
• /
• no.3 s.181
• /
• pp.8-9
• /
• 1994